Persönlicher Status und Werkzeuge

Home Research Romeo: Body, hand and object tracking in everyday activities

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
research:romeo_everyday [2011/08/18 16:48]
weikersd
research:romeo_everyday [2011/08/18 16:50] (current)
weikersd
Line 1: Line 1:
-====== Romeo: Body, hand and object tracking in everyday activities ====== 
 ~~NOTOC~~ ~~NOTOC~~
 +
 +====== Romeo: Body, hand and object tracking in everyday activities ======
  
 The Romeo framework is a markerless visually tracker framework for articulated and rigid models with special application to tracking the human hand and several objects in complex manipulation activities. We are using image streams from three high definition cameras which are segmented using color histograms and additionally used to build a voxel representation of the scene context. The detailed representation of the human hand in complex articulations and object manipulation scenarios involves a high-dimensional state space of 32 and more degrees of freedom. Additional 75+ parameters arise when adapting the hand CAD model to the human instructor'​s hand in an initialization step. To be able to find accurate tracking solutions, we use particle filter based tracking algorithms and local optimization techniques. Image evaluation is boosted by using the latest GPGPU acceleration framework OpenCL along with multi-processor CPU evaluation. The Romeo framework is a markerless visually tracker framework for articulated and rigid models with special application to tracking the human hand and several objects in complex manipulation activities. We are using image streams from three high definition cameras which are segmented using color histograms and additionally used to build a voxel representation of the scene context. The detailed representation of the human hand in complex articulations and object manipulation scenarios involves a high-dimensional state space of 32 and more degrees of freedom. Additional 75+ parameters arise when adapting the hand CAD model to the human instructor'​s hand in an initialization step. To be able to find accurate tracking solutions, we use particle filter based tracking algorithms and local optimization techniques. Image evaluation is boosted by using the latest GPGPU acceleration framework OpenCL along with multi-processor CPU evaluation.
Last edited 18.08.2011 16:50 by weikersd